Qwen 3.8-Max Now on Modal: 2.4T Params, 1M Context, Custom DFlash Speculator

AAAzzam · x · 2026-08-14

Alibaba's Qwen 3.8-Max is now available on Modal, with full 1M context window and a custom DFlash speculator trained on tool-call-heavy data. The model has 2.4T parameters (95B active) and is a Modal call away.

Related event: Qwen 3.8-Max Debuts on Modal with 1M Context(2 posts)→

Original post →

More from Infra

Infra channel →